*/
u64 count_range_bits(struct extent_io_tree *tree,
u64 *start, u64 search_end, u64 max_bytes,
- unsigned long bits)
+ unsigned long bits, int contig)
{
struct rb_node *node;
struct extent_state *state;
u64 cur_start = *start;
u64 total_bytes = 0;
+ u64 last = 0;
int found = 0;
if (search_end <= cur_start) {
state = rb_entry(node, struct extent_state, rb_node);
if (state->start > search_end)
break;
- if (state->end >= cur_start && (state->state & bits)) {
+ if (contig && found && state->start > last + 1)
+ break;
+ if (state->end >= cur_start && (state->state & bits) == bits) {
total_bytes += min(search_end, state->end) + 1 -
max(cur_start, state->start);
if (total_bytes >= max_bytes)
*start = state->start;
found = 1;
}
+ last = state->end;
+ } else if (contig && found) {
+ break;
}
node = rb_next(node);
if (!node)
bio_get(bio);
if (tree->ops && tree->ops->submit_bio_hook)
- tree->ops->submit_bio_hook(page->mapping->host, rw, bio,
+ ret = tree->ops->submit_bio_hook(page->mapping->host, rw, bio,
mirror_num, bio_flags, start);
else
submit_bio(rw, bio);
nr = bio_get_nr_vecs(bdev);
bio = btrfs_bio_alloc(bdev, sector, nr, GFP_NOFS | __GFP_HIGH);
+ if (!bio)
+ return -ENOMEM;
bio_add_page(bio, page, page_size, offset);
bio->bi_end_io = end_io_func;
static void set_page_extent_head(struct page *page, unsigned long len)
{
+ WARN_ON(!PagePrivate(page));
set_page_private(page, EXTENT_PAGE_PRIVATE_FIRST_PAGE | len << 2);
}
BUG_ON(extent_map_end(em) <= cur);
BUG_ON(end < cur);
- if (test_bit(EXTENT_FLAG_COMPRESSED, &em->flags))
+ if (test_bit(EXTENT_FLAG_COMPRESSED, &em->flags)) {
this_bio_flag = EXTENT_BIO_COMPRESSED;
+ extent_set_compress_type(&this_bio_flag,
+ em->compress_type);
+ }
iosize = min(extent_map_end(em) - cur, end - cur + 1);
cur_end = min(extent_map_end(em) - 1, end);
ret = __extent_read_full_page(tree, page, get_extent, &bio, 0,
&bio_flags);
if (bio)
- submit_one_bio(READ, bio, 0, bio_flags);
+ ret = submit_one_bio(READ, bio, 0, bio_flags);
return ret;
}
* at this point we can safely clear everything except the
* locked bit and the nodatasum bit
*/
- clear_extent_bit(tree, start, end,
+ ret = clear_extent_bit(tree, start, end,
~(EXTENT_LOCKED | EXTENT_NODATASUM),
0, 0, NULL, mask);
+
+ /* if clear_extent_bit failed for enomem reasons,
+ * we can't allow the release to continue.
+ */
+ if (ret < 0)
+ ret = 0;
+ else
+ ret = 1;
}
return ret;
}
return sector;
}
+/*
+ * helper function for fiemap, which doesn't want to see any holes.
+ * This maps until we find something past 'last'
+ */
+static struct extent_map *get_extent_skip_holes(struct inode *inode,
+ u64 offset,
+ u64 last,
+ get_extent_t *get_extent)
+{
+ u64 sectorsize = BTRFS_I(inode)->root->sectorsize;
+ struct extent_map *em;
+ u64 len;
+
+ if (offset >= last)
+ return NULL;
+
+ while(1) {
+ len = last - offset;
+ if (len == 0)
+ break;
+ len = (len + sectorsize - 1) & ~(sectorsize - 1);
+ em = get_extent(inode, NULL, 0, offset, len, 0);
+ if (!em || IS_ERR(em))
+ return em;
+
+ /* if this isn't a hole return it */
+ if (!test_bit(EXTENT_FLAG_VACANCY, &em->flags) &&
+ em->block_start != EXTENT_MAP_HOLE) {
+ return em;
+ }
+
+ /* this is a hole, advance to the next extent */
+ offset = extent_map_end(em);
+ free_extent_map(em);
+ if (offset >= last)
+ break;
+ }
+ return NULL;
+}
+
int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
__u64 start, __u64 len, get_extent_t *get_extent)
{
u32 flags = 0;
u32 found_type;
u64 last;
+ u64 last_for_get_extent = 0;
u64 disko = 0;
+ u64 isize = i_size_read(inode);
struct btrfs_key found_key;
struct extent_map *em = NULL;
struct extent_state *cached_state = NULL;
struct btrfs_path *path;
struct btrfs_file_extent_item *item;
int end = 0;
- u64 em_start = 0, em_len = 0;
+ u64 em_start = 0;
+ u64 em_len = 0;
+ u64 em_end = 0;
unsigned long emflags;
- int hole = 0;
if (len == 0)
return -EINVAL;
return -ENOMEM;
path->leave_spinning = 1;
+ /*
+ * lookup the last file extent. We're not using i_size here
+ * because there might be preallocation past i_size
+ */
ret = btrfs_lookup_file_extent(NULL, BTRFS_I(inode)->root,
path, inode->i_ino, -1, 0);
if (ret < 0) {
btrfs_item_key_to_cpu(path->nodes[0], &found_key, path->slots[0]);
found_type = btrfs_key_type(&found_key);
- /* No extents, just return */
+ /* No extents, but there might be delalloc bits */
if (found_key.objectid != inode->i_ino ||
found_type != BTRFS_EXTENT_DATA_KEY) {
- btrfs_free_path(path);
- return 0;
+ /* have to trust i_size as the end */
+ last = (u64)-1;
+ last_for_get_extent = isize;
+ } else {
+ /*
+ * remember the start of the last extent. There are a
+ * bunch of different factors that go into the length of the
+ * extent, so its much less complex to remember where it started
+ */
+ last = found_key.offset;
+ last_for_get_extent = last + 1;
}
- last = found_key.offset;
btrfs_free_path(path);
+ /*
+ * we might have some extents allocated but more delalloc past those
+ * extents. so, we trust isize unless the start of the last extent is
+ * beyond isize
+ */
+ if (last < isize) {
+ last = (u64)-1;
+ last_for_get_extent = isize;
+ }
+
lock_extent_bits(&BTRFS_I(inode)->io_tree, start, start + len, 0,
&cached_state, GFP_NOFS);
- em = get_extent(inode, NULL, 0, off, max - off, 0);
+
+ em = get_extent_skip_holes(inode, off, last_for_get_extent,
+ get_extent);
if (!em)
goto out;
if (IS_ERR(em)) {
}
while (!end) {
- hole = 0;
- off = em->start + em->len;
- if (off >= max)
- end = 1;
+ u64 offset_in_extent;
- if (em->block_start == EXTENT_MAP_HOLE) {
- hole = 1;
- goto next;
- }
+ /* break if the extent we found is outside the range */
+ if (em->start >= max || extent_map_end(em) < off)
+ break;
- em_start = em->start;
- em_len = em->len;
+ /*
+ * get_extent may return an extent that starts before our
+ * requested range. We have to make sure the ranges
+ * we return to fiemap always move forward and don't
+ * overlap, so adjust the offsets here
+ */
+ em_start = max(em->start, off);
+ /*
+ * record the offset from the start of the extent
+ * for adjusting the disk offset below
+ */
+ offset_in_extent = em_start - em->start;
+ em_end = extent_map_end(em);
+ em_len = em_end - em_start;
+ emflags = em->flags;
disko = 0;
flags = 0;
+ /*
+ * bump off for our next call to get_extent
+ */
+ off = extent_map_end(em);
+ if (off >= max)
+ end = 1;
+
if (em->block_start == EXTENT_MAP_LAST_BYTE) {
end = 1;
flags |= FIEMAP_EXTENT_LAST;
flags |= (FIEMAP_EXTENT_DELALLOC |
FIEMAP_EXTENT_UNKNOWN);
} else {
- disko = em->block_start;
+ disko = em->block_start + offset_in_extent;
}
if (test_bit(EXTENT_FLAG_COMPRESSED, &em->flags))
flags |= FIEMAP_EXTENT_ENCODED;
-next:
- emflags = em->flags;
free_extent_map(em);
em = NULL;
- if (!end) {
- em = get_extent(inode, NULL, 0, off, max - off, 0);
- if (!em)
- goto out;
- if (IS_ERR(em)) {
- ret = PTR_ERR(em);
- goto out;
- }
- emflags = em->flags;
- }
-
- if (test_bit(EXTENT_FLAG_VACANCY, &emflags)) {
+ if ((em_start >= last) || em_len == (u64)-1 ||
+ (last == (u64)-1 && isize <= em_end)) {
flags |= FIEMAP_EXTENT_LAST;
end = 1;
}
- if (em_start == last) {
+ /* now scan forward to see if this is really the last extent. */
+ em = get_extent_skip_holes(inode, off, last_for_get_extent,
+ get_extent);
+ if (IS_ERR(em)) {
+ ret = PTR_ERR(em);
+ goto out;
+ }
+ if (!em) {
flags |= FIEMAP_EXTENT_LAST;
end = 1;
}
-
- if (!hole) {
- ret = fiemap_fill_next_extent(fieinfo, em_start, disko,
- em_len, flags);
- if (ret)
- goto out_free;
- }
+ ret = fiemap_fill_next_extent(fieinfo, em_start, disko,
+ em_len, flags);
+ if (ret)
+ goto out_free;
}
out_free:
free_extent_map(em);
#endif
eb = kmem_cache_zalloc(extent_buffer_cache, mask);
+ if (eb == NULL)
+ return NULL;
eb->start = start;
eb->len = len;
spin_lock_init(&eb->lock);
}
if (!PageUptodate(p))
uptodate = 0;
- unlock_page(p);
+
+ /*
+ * see below about how we avoid a nasty race with release page
+ * and why we unlock later
+ */
+ if (i != 0)
+ unlock_page(p);
}
if (uptodate)
set_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags);
atomic_inc(&eb->refs);
spin_unlock(&tree->buffer_lock);
radix_tree_preload_end();
+
+ /*
+ * there is a race where release page may have
+ * tried to find this extent buffer in the radix
+ * but failed. It will tell the VM it is safe to
+ * reclaim the, and it will clear the page private bit.
+ * We must make sure to set the page private bit properly
+ * after the extent buffer is in the radix tree so
+ * it doesn't get lost
+ */
+ set_page_extent_mapped(eb->first_page);
+ set_page_extent_head(eb->first_page, eb->len);
+ if (!page0)
+ unlock_page(eb->first_page);
return eb;
free_eb:
+ if (eb->first_page && !page0)
+ unlock_page(eb->first_page);
+
if (!atomic_dec_and_test(&eb->refs))
return exists;
btrfs_release_extent_buffer(eb);
continue;
lock_page(page);
+ WARN_ON(!PagePrivate(page));
+
+ set_page_extent_mapped(page);
if (i == 0)
set_page_extent_head(page, eb->len);
- else
- set_page_private(page, EXTENT_PAGE_PRIVATE);
clear_page_dirty_for_io(page);
spin_lock_irq(&page->mapping->tree_lock);
for (i = start_i; i < num_pages; i++) {
page = extent_buffer_page(eb, i);
+
+ WARN_ON(!PagePrivate(page));
+
+ set_page_extent_mapped(page);
+ if (i == 0)
+ set_page_extent_head(page, eb->len);
+
if (inc_all_pages)
page_cache_get(page);
if (!PageUptodate(page)) {
projects / mv-sheeva.git / blobdiff